Instructions to use lucataco/ReplicateFluxLoRA with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use lucataco/ReplicateFluxLoRA with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", torch_dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("lucataco/ReplicateFluxLoRA") prompt = "a boat in the style of TOK" image = pipe(prompt).images[0] - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
metadata
license: other
license_name: flux-1-dev-non-commercial-license
license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md
language:
- en
tags:
- flux
- diffusers
- lora
- replicate
base_model: black-forest-labs/FLUX.1-dev
pipeline_tag: text-to-image
instance_prompt: TOK
widget:
- text: a boat in the style of TOK
output:
url: >-
https://replicate.delivery/yhqm/z7f2OBcvga07dCoJ4FeRGZCbE5PvipLhogPhEeU7BazIg5lmA/out-0.webp
- text: a car in the style of TOK
output:
url: >-
https://replicate.delivery/yhqm/c9Bh6p0VuSoJKtNseie38Kl9piM5Fmnw49AyxfuI7e3cIzLNB/out-0.webp
Flux Mona Lisa

- Prompt
- a boat in the style of TOK

- Prompt
- a car in the style of TOK
Trained on Replicate using:
https://replicate.com/ostris/flux-dev-lora-trainer/train
Trigger words
You should use TOK to trigger the image generation.
Training details
Watercolor style trained for 1000 steps
prompt: "a boat in the style of TOK"